© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10254
    Prev
    Next
    INDEX
    Explanations

    method signatures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.39
    WriteLiteral
    -0.38
     iden
    -0.38
    ześnie
    -0.37
    ModelAdmin
    -0.36
     employes
    -0.35
     identi
    -0.35
    رشف
    -0.34
     exh
    -0.34
     tpu
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.60
    Portály
    0.57
    +:+
    0.55
    AutoScaleMode
    0.53
    MemoryWarning
    0.52
    ContentAsync
    0.52
     AttributeSet
    0.51
    ########.
    0.50
    LookAnd
    0.50
    WebServlet
    0.50
    Activations Density 0.076%

    No Known Activations